We initiate a systematic investigation of distribution testing in the framework of algorithmic replicability. Specifically, given independent samples from a collection of probability distributions, the goal is to characterize the sample complexity of replicably testing natural properties of the underlying distributions. On the algorithmic front, we develop new replicable algorithms for testing closeness and independence of discrete distributions. On the lower bound front, we develop a new methodology for proving sample complexity lower bounds for replicable testing that may be of broader interest. As an application of our technique, we establish near-optimal sample complexity lower bounds for replicable uniformity testing--answering an open question from prior work--and closeness testing.

Neural Information Processing Systems http://nips.cc/

's matching capacity will be reduced

This often results in data being sparse and biased towards popular locations, exhibiting a severe long-tail effect.

Many attempts have been made throughout the last thirty years.

Running a large number of algorithm-hyperparameter pairs many times is very computationally expensive.

In section 7 we introduce the constrained architecture of Time Distributed Convolutional Neural Networks. A validation set was used to monitor the inference.